Closed ghost closed 6 years ago
Hi @rdiazgarHP
You can also restrict the matrix to be rotations only. Currently the 3x3 matrix has a more free form such that it can also skew or scale the point clouds. For the 64x64 transformation matrix we found a regularization of orthogonality makes optimization more controllable and leads to better performance.
Best, Charles
I see. Thanks for the clarification!
Hi @rdiazgarHP
You can also restrict the matrix to be rotations only. Currently the 3x3 matrix has a more free form such that it can also skew or scale the point clouds. For the 64x64 transformation matrix we found a regularization of orthogonality makes optimization more controllable and leads to better performance.
Best, Charles
Hello @charlesq34! How can the rotation matrix be forced to represent only rotations? Moreover, would be a good idea to substitute T-Net with data augmentation (e.g. every kind of rotation)?
Hi,
I was just wondering. Is there any particular reason for not enforcing orthogonality to the transform_XYZ net, but to do so in the transform_feat one? It seems to me that the first T-net can roam free to transform the input cloud, and only the second T-net contributes to the loss by orthogonal enforcement. Why not enforce the first T-net too?
Regards, Raul